-
Notifications
You must be signed in to change notification settings - Fork 93
MCP Security Vulnerabilities #94
Copy link
Copy link
Open
Labels
domain:surfacesAgent UI, Telegram, WhatsApp, Slack/Discord, mobileAgent UI, Telegram, WhatsApp, Slack/Discord, mobilep1medium prioritymedium prioritysecuritySecurity-sensitive changesSecurity-sensitive changestrack:consumer-appHermes-competitor consumer product — mobile-first, voice + messaging + memory + skillsHermes-competitor consumer product — mobile-first, voice + messaging + memory + skills
Description
Metadata
Metadata
Assignees
Labels
domain:surfacesAgent UI, Telegram, WhatsApp, Slack/Discord, mobileAgent UI, Telegram, WhatsApp, Slack/Discord, mobilep1medium prioritymedium prioritysecuritySecurity-sensitive changesSecurity-sensitive changestrack:consumer-appHermes-competitor consumer product — mobile-first, voice + messaging + memory + skillsHermes-competitor consumer product — mobile-first, voice + messaging + memory + skills
RE: #82
Security Scan Results
Security Score: 55/100
Risk Level: high
Scan Date: 2025-08-21
Score starts at 100, deducts points for security issues, and adds points for security best practices
Security Findings
Medium Severity Issues
semgrep: Use of os.system() with dynamic input detected. This can lead to command injection.
Location: src/gaia/llm/lemonade_client.py
Line: 225
semgrep: Use of subprocess with shell=True detected. This can be dangerous if used with untrusted input.
Location: installer/installer_utils.py
Line: 87
... and 16 more medium severity issues
This security assessment was conducted by MSeeP.ai, an independent security validation service for MCP servers. Visit our website to learn more about our security reviews.